Comparison of Time and Spectral Domain Features on Postural Signals Utilizing Neural Networks

Andreas Fey, David Sommer, Martin Golz

2005

Abstract

Human postural equilibrium is the result of complex control processes. Nevertheless these processes are taken for granted in our daily life, disturbance or degeneration of a single system involved in these processes leads to a variety of diseases, which pile up with age. Therefore, investigation of postural signals is the aim of many clinical and biophysical studies, in order to recognize diseases early and to improve the precision of diagnostics. In order to analyze posturographic signals we conducted a pilot study to measure body sway of nine healthy subjects during four trials with different acoustic and visual impairments, in order to detect their influence on stance. Ten time domain and five spectral domain feature extraction methods were applied on segmented raw data and classified by five different classification methods. The test errors were empirically minimized first by estimating best parameters for each feature extraction method, yielding to an optimal combination of feature extraction and classification methods. It turned out, that Burg autoregressive method of power spectral density estimation and Optimized Learning Vector Quantization was the best method combination. The classification task “no impairment” versus “visual impairment”, i.e. “eyes open” versus “eyes closed”, showed best discriminative performance indicated by mean test errors of 2.2%. The pilot study pointed out, that the established biosignal analysis system gained a high sensitivity on small postural influences.

References

  1. Chiari, L., Rocchi, L. and Cappello, A.: Stabilometric parameters are affected by anthropometry and foot placement. Clinical Biomechanics (2002) 666-677
  2. Clair, K.L. and Riach, C.: Postural stability measures: what to measure and for how long. Clinical Biomechanics (1996) 176-178
  3. Collins, J.J. and De Luca, C.J.: Upright, correlated random walks: A statisticalbiomechanics approach to the human postural control system. Chaos (1995) 57-63
  4. Fransson, P.A. et al.: Adaption to vibratatory perturbations in postural control. IEEE engineering in medicine and biology Magazine (2003) 53-57
  5. Fritzke, B.: Vektorbasierte Neuronale Netze. Universität Erlangen - Nürnberg (1998)
  6. Harris, C.S.: Effects of increasing intensity levels of intermitted and continuous 1000 Hz tones on human equilibrium. Perceptual and Motor skills (1972) 395-405
  7. Joachims, T.: Learning to classify text using support vector machines. KluwerAc.Pub.(2002)
  8. Kohonen, T.: Learning Vector Quantization. Neural Networks (1988) 303-306
  9. Kohonen, T.: Self organizing maps. Berlin, Heidelberg, New York: Springer Verlag (2001)
  10. Loughlin, P.J. and Redfern, M.S.: Spectral characteristics if visually induced postural sway in healthy elderly and healthy young subjects. IEEE Trans.Neur.Sys. (2001) 24-30
  11. Loughlin, P. and Redfern, M.: Analysis and modelling of human postural control. IEEE Engineering in Medicine and Biology Magazine (2003) 18
  12. Nakagawa, H. et al.: The contribution of proprioception to posture control in normal subjects. Acta Otolaryngol (1993) 112-116
  13. Oie, K.S. et al. Multisensory fusion: simultaneous re-weighting of vision and touch for the control of human posture. Cognitive Brain Research (2002) 164-176
  14. Oostervelt, W.J., Polman, A.R. and Schoonheyt, J.: Vestibular implications of noise-inducd hearing loss. British Journal of Audiology (1982) 227-232
  15. Percival, D.B. et al. : Spectral analysis for physical applications. Cambridge University Press (1993)
  16. Raper, S.A. and Soames, R.W.: The influence of moving auditory fields on postural sway behaviour in man. European Journal of Applied Physiology (1992) 241-245.
  17. Sakellari, V. and Soames, R.W.: Auditory and visual interactions in postural stabilization. Ergonomics (1996) 634-648
  18. Vapnik, V.: Statistical Learning Theory. Chichester, GB: Wiley (1998)
Download


Paper Citation


in Harvard Style

Fey A., Sommer D. and Golz M. (2005). Comparison of Time and Spectral Domain Features on Postural Signals Utilizing Neural Networks . In Proceedings of the 1st International Workshop on Biosignal Processing and Classification - Volume 1: BPC, (ICINCO 2005) ISBN 972-8865-35-X, pages 42-49. DOI: 10.5220/0001196100420049


in Bibtex Style

@conference{bpc05,
author={Andreas Fey and David Sommer and Martin Golz},
title={Comparison of Time and Spectral Domain Features on Postural Signals Utilizing Neural Networks},
booktitle={Proceedings of the 1st International Workshop on Biosignal Processing and Classification - Volume 1: BPC, (ICINCO 2005)},
year={2005},
pages={42-49},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001196100420049},
isbn={972-8865-35-X},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 1st International Workshop on Biosignal Processing and Classification - Volume 1: BPC, (ICINCO 2005)
TI - Comparison of Time and Spectral Domain Features on Postural Signals Utilizing Neural Networks
SN - 972-8865-35-X
AU - Fey A.
AU - Sommer D.
AU - Golz M.
PY - 2005
SP - 42
EP - 49
DO - 10.5220/0001196100420049